add-icon-mapping

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard development and search tools, including bun run type-check for verification, grep for searching the codebase, and git for verifying commit contents.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as user requests and Linear issue descriptions to identify required mapping changes.
  • Ingestion points: Data enters the agent's context through user prompts or referenced Linear issues mentioned in the skill's description.
  • Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions within the processed data.
  • Capability inventory: The skill includes instructions to modify TypeScript source files and execute repository-specific shell commands.
  • Sanitization: No explicit sanitization or filtering of external input is specified before it is used in code mappings or regex patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 09:41 AM
Security Audit — agent-trust-hub — add-icon-mapping